Yian Zhang
Research Staff at NVIDIA
Palo Alto, California, United States
Summary
🤩
Rockstar🎓
Top SchoolYian Zhang is an NLP researcher and research staff engineer with seven years of experience building and evaluating language and multimodal models, currently working at NVIDIA on reinforcement learning and Nemotron systems after recent roles at AWS focused on retrieval-augmented generation. He combines a strong academic background from Stanford and NYU with practical ML engineering—contributing backend metrics and evaluation code to the widely used HELM framework for holistic LM assessment. Yian has shipped production features and prototypes across industry internships at ByteDance and AWS AI Labs, including domain adaptation via PEFT and multi-purpose slot-filling systems. Based in Palo Alto, he bridges research rigor and production readiness, often surfacing evaluation insights that improve model transparency and robustness.
7 years of coding experience
1 year of employment as a software developer
Visiting Research Intern at AIM Lab, Visiting Research Intern at AIM Lab at New York University Abu DhabiBachelor of Science Computer Science, Bachelor of Science Computer Science at New York UniversityBachelor of Science Computer Science, Bachelor of Science Computer Science at NYU ShanghaiMaster of Science Computer Science, Master of Science Computer Science at Stanford University
Chinese, Chinese
Github Skills (7)
machine-learning10
nlp10
python10
natural-language-processing10
language-modeling10
metric10
testing10
Programming languages (2)
Github contributions (5)
stanford-crfm/helm
Jan 2022 - Mar 2023
Holistic Evaluation of Language Models (HELM), a framework to increase the transparency of language models (https://arxiv.org/abs/2211.09110). This framework is also used to evaluate text-to-image models in HEIM (https://arxiv.org/abs/2311.04287) and vision-language models in VHELM (https://arxiv.org/abs/2410.07112).
Role in this project:
Back-end Developer & ML Engineer
Back-end Developer & ML EngineerContributions:24 reviews, 195 commits, 30 PRs in 1 year 2 months
Contributions summary:Yian's commits primarily focused on implementing and testing core machine learning metrics and functionalities within the HELM framework. They implemented language model (LM) and perplexity metrics, including nll, and incorporated byte-level and gpt3-specific metrics. The commits also included the setup of a testing scenario using a fake Twitter AAE dataset, demonstrating an integration of the existing framework to evaluate the performance of language models.
nlparxivabsberthelm
YianZhang/ONLSTM-analysis
Oct 2020 - Oct 2020
Contributions:10 commits, 7 pushes, 1 branch in 1 day
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.